StartupBerkeley, CA · Est. 2020
Arize AI
Observability and evaluation for AI — makers of OSS Phoenix.
Arize traces and evaluates LLM and agent systems in production; their open-source Phoenix tracer is a common instrumentation choice for agent harnesses that need to be debuggable.
Pros & cons
Each point cites its sources and says what kind of evidence backs it. A second reviewer tried to refute every claim before it was kept.
Pros
- MetadataPhoenix is free to self-host and very active (about 12k stars, commits on 29 Oct 2026).[1][2]
- User reportsBuilt on OpenTelemetry and OpenInference, so traces are portable; users praise OpenInference, and a community proxy sends Claude Code spans to Phoenix.[1][2]
- User reportsPractitioners use Phoenix for LLM-as-judge plus code-based evals and continuous analysis of production traces.[1][2]
- DocsEvery AX plan, including Free, has unlimited users and evals, and AX Pro costs $50/month.[1]
Cons
- MetadataPhoenix uses the Elastic License 2.0, which is source-available rather than OSI open source and restricts offering it as a managed service.[1]
- DocsAX Free caps you at 25k spans a month with 15-day retention, and Pro raises that only to 50k spans and 30 days.[1]
- DocsSelf-hosted AX, SSO and audit logs are Enterprise-only.[1]
- User reportsOne user found Arize's Claude Code tracing setup heavyweight, and others dropped Phoenix after reviewing its site.[1][2]
- MetadataPhoenix has about 1,000 open GitHub issues.[1]
- Best for
- Teams that want OpenTelemetry-native LLM tracing and evals they can run themselves with Phoenix, with a hosted option later.
- Watch out for
- AX Free and Pro have low span and retention caps, and ELv2 limits offering Phoenix as a service.
Assessed Oct 29, 2026 · adversarially reviewedSuggest a correction
People
Co-founder & Chief Product Officer
Evals & benchmarks
Co-founder & CEO
Evals & benchmarks
Open roles (20)
- Director of Sales, APJ
Remote (SIngapore) · Posted Nov 10, 2026
Go-to-marketRemote - Senior AI Product Manager, Evals & Annotations
United States (Remote) · Posted Nov 10, 2026
Product & designRemote - Enterprise Account Executive, MEA
Remote · Posted Nov 3, 2026
Go-to-marketRemote - Head of Growth Marketing
San Francisco, CA · Posted Oct 22, 2026
Go-to-market - Principal of Technical Content & Editorial
San Francisco, CA · Posted Oct 22, 2026
Go-to-market
Their open-source work
Python · ≈12k stars · Elastic-2.0
Arize-ai/phoenix
Open-source AI observability and evals from Arize.
Maintained by Arize AI
arize-phoenix-v22.0.0releasedActivity
- Last push
- · yesterday
- Latest release
- arize-phoenix-v22.0.0
· yesterday - Last 90 days
- 20+ releases
arize-phoenix-v22.0.0arize-phoenix: v22.0.0
· yesterday22.0.0 (2026-11-20) MIGRATION Features add type column to generative_models (3047aab) cost-tracking: calculate costs for DECISION spans (#17764) (0f83453) cost-tracking: calculate costs for EMBEDDING spans (#17788) (0f39d64) cost-tracking: expose generative model type in…
arize-phoenix-v21.3.0arize-phoenix: v21.3.0
· yesterday21.3.0 (2026-11-20) Features brand: set the Arize Phoenix wordmark in Geist (#18086) (b176371) cli: add dataset label assignment commands (#17973) (0b821b2) pxi: refresh recommended models and preserve chat transcripts (#18101) (4270bce) Bug Fixes build: let the publish wheel…
- · 2d ago
Minor Changes 0b821b2: Add px dataset-labels list, add, remove, and replace commands to manage existing label assignments by dataset name or GlobalID, including explicitly clearing all assignments. Patch Changes 4270bce: Limit PXI to two recommended models per provider: Claude…
- · 2d ago
Patch Changes 02ed180: Remove Slack community links from the package README Updated dependencies [02ed180] @arizeai/phoenix-config@0.5.2 @arizeai/phoenix-otel@3.1.1
- · 2d ago
Patch Changes 02ed180: Remove Slack community links from the package README Updated dependencies [02ed180] @arizeai/phoenix-config@0.5.2
Checked against GitHub on Nov 21, 2026. Release notes are shortened to plain text.
On X
Posts by the company and its team, shown as plain text; “Load on X” loads X's script for that post, which may set cookies.
Aparna Dhinakaran · Jul 3, 2026
Videos

AI Engineer · Oct 27, 2026
Stop Giving Your Agent Tools. Give It a Sandbox - Mikyo King, Arize AI
Security & sandboxes · Harness engineering

AI Engineer · Oct 27, 2026
We Kept Rebuilding Our AI Agent. Here's What Survived - Fuad Ali, Arize AI
Harness engineering · Talks & interviews

AI Engineer · Oct 26, 2026
Agents That Self Improve While You Sleep - Fuad Ali, Arize AI
Harness engineering
Neighbours in the directory
San Francisco, CA · Est. 2022
The de-facto standard toolkit for building LLM applications and agents.
LangChain makes the LangChain framework and LangGraph, the low-level orchestration standard for stateful, controllable agents, plus the LangSmith platform for tracing, evaluating and monitoring them in production.
~$75M raised
San Francisco, CA · Est. 2023
Enterprise-grade evals, data and AI gateway.
Braintrust turns prompts and agent traces into testable datasets and CI, plus an inference gateway — helping teams measure whether harness changes actually improve agent quality.
San Francisco, CA · Est. 2021
Evaluation platform for LLMs and agentic systems.
Galileo (makers of the Luna evaluation models) scores agent runs for hallucination, tool-use errors and task completion — automated quality gates for harness engineering. Cisco acquired Galileo in April 2026 and folded it into Splunk's agent observability; the old rungalileo.io domain has lapsed.
Connections
Relations from the Harness Hub knowledge graph, as charted in the State of Harness reports.
Maintains · 1
- PhoenixProject
Similar entries · 7
- Apache BurrProject
- Bento LabsStartup
- LaminarStartup
- LangfuseProject
- Langfuse (ClickHouse)Startup
- OpikProject
and 1 more